Rolv-Arild/replay-pretraining

Rocket League pretraining from replay files

37
/ 100
Emerging

Are you a Rocket League player or enthusiast curious about how AI can learn from human gameplay? This project helps train an AI agent to mimic human behavior in Rocket League. It takes standard Rocket League replay files as input and outputs a trained AI model capable of emulating human actions.

No commits in the last 6 months.

Use this if you want to leverage existing human gameplay data from Rocket League replays to create AI agents that behave more like players.

Not ideal if you're looking for an AI agent trained exclusively through self-play reinforcement learning, aiming for purely optimal (non-human-like) performance.

Rocket-League AI-training Esports-analytics Gameplay-emulation Reinforcement-learning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

37

Forks

5

Language

Python

License

GPL-3.0

Last pushed

Apr 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Rolv-Arild/replay-pretraining"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.